We propose methods to estimate sufficient reductions in matrix-valued predictors for regression or classification. We assume that the first moment of the predictor matrix given the response can be decomposed into a row and column component via a Kronecker product structure. We obtain least squares and maximum likelihood estimates of the sufficient reductions in the matrix predictors, derive statistical properties of the resulting estimates and present fast computational algorithms with assured convergence. The performance of the proposed approaches in regression and classification is compared in simulations.We illustrate the methods on two examples, using longitudinally measured serum biomarker and neuroimaging data.Background and study aims? The Japan Narrow-band imaging (NBI) Expert Team (JNET) classification was proposed for evaluating colorectal lesions. However, it remains unknown whether the JNET classification can be applied to magnifying endoscopy with image-enhanced endoscopies other than NBI. This study aimed to compare the diagnostic ability of JNET classification by magnifying endoscopy with blue laser imaging (ME-BLI) and with ME-NBI. Patients and methods? We retrospectively assessed consecutive patients diagnosed per the JNET classification by ME-BLI (BLI group) or ME-NBI (NBI group) between March 2014 and June 2017. We compared the diagnostic value of JNET classification between the groups with one-to-one propensity score matching. Results? Four hundred and seventy-one propensity score-matched pairs of lesions were analyzed. In the BLI and NBI groups, the overall diagnostic accuracies were 92.1?% and 91.7?%, respectively, and those for differentiating between neoplastic and non-neoplastic polyps were 96.6?% and 96.8?%, respectively. The positive predictive value by each JNET classification in BLI vs. NBI group was 90.6?% vs. 96.2?% in Type 1, 94.3?% vs. 94.6?% in Type 2A, 57.7?% vs. 42.3?% in Type 2B, and 100?% vs. 91.7?% in Type 3.?The negative predictive value was 97.0?% vs. 96.9?% in Type 1, 88.1?% vs. 82.8?% in Type 2A, 98.0?% vs. 98.2?% in Type 2B, and 98.5?% vs. 98.7?% in Type 3. No statistical difference in the diagnostic results was found between the groups. Conclusions? The diagnostic ability of the JNET classification by ME-BLI and ME-NBI was comparable, with the former also applicable for diagnosis of colorectal lesions.Background and study aims ?Detecting colorectal neoplasia is the goal of high-quality screening and surveillance colonoscopy, as reflected by high adenoma detection rate (ADR) and adenomas per colonoscopy (APC). The aim of our study was to evaluate the performance of a novel artificial intelligence (AI)-aided polyp detection device, Skout, with the primary endpoints of ADR and APC in routine colonoscopy. Patients and methods ?We compared ADR and APC in a cohort of outpatients undergoing routine high-resolution colonoscopy with and without the use of a real-time, AI-aided polyp detection device. Patients undergoing colonoscopy with Skout were enrolled in a single-arm, unblinded, prospective trial and the results were compared with a historical cohort. All resected polyps were examined histologically. Results ?Eighty-three patients undergoing screening and surveillance colonoscopy at an outpatient endoscopy center were enrolled and outcomes compared with 283 historical control patients. Overall, ADR with and without Skout was 54.2?% and 40.6?% respectively ( P ?=?0.028) and 53.6?% and 30.8?%, respectively, in screening exams ( P ?=?0.024). Overall, APC rate with and without Skout was 1.46 and 1.01, respectively, ( P ?=?0.104) and 1.18 and 0.50, respectively, in screening exams ( P ?=?0.002). Overall, true histology rate (THR) with and without Skout was 73.8?% and 78.4?%, respectively, ( P ?=?0.463) and 75.0?% and 71.0?%, respectively, in screening exams ( P ?=?0.731). Conclusion ?We have demonstrated that our novel AI-aided polyp detection device increased the ADR in a cohort of patients undergoing screening and surveillance colonoscopy without a significant concomitant increase in hyperplastic polyp resection. AI-aided colonoscopy has the potential for improving the outcomes of patients undergoing colonoscopy.Background and study aims ?We previously reported a case series of our first 182 colorectal endoscopic submucosal dissections (ESDs). In the initial series, 155 ESDs had been technically feasible, with 137 en bloc resections and 97 en bloc resections with free margins (R0). Here, we present long-term follow-up data, with particular emphasis on cases where either en bloc resection was not achieved or en bloc resection resulted in positive margins (R1). Patients and methods ?Between September 2012 and October 2015, we performed 182 consecutive ESD procedures in 178 patients (median size 41.0?±?17.4 mm; localization rectum vs. proximal rectum 63 vs. 119). Data on follow-up were obtained from our endoscopy database and from referring physicians. Results ?Of the initial cohort, 11 patients underwent surgery; follow-up data were available for 141 of the remaining 171 cases (82,5?%) with a median follow-up of 2.43 years (range 0.15-6.53). Recurrent adenoma was observed in 8 patients (n?=?2 after margin positive en bloc ESD; n?=?6 after fragmented resection). Recurrence rates were lower after en bloc resection, irrespective of involved margins (1.8 vs. 18,2?%; P? less then ?0.01). All recurrences were low-grade adenomas and could be managed endoscopically. Conclusions ?The rate of recurrence is low after en bloc ESD, in particular if a one-piece resection can be achieved. Recurrence after fragmented resection is comparable to published data on piecemeal mucosal resection.Background and study aims ?In borderline resectable/locally advanced pancreatic ductal adenocarcinoma (PDAC), stereotactic body radiation therapy (SBRT) is an emerging neoadjuvant treatment option. Endoscopic ultrasound (EUS)-guided insertion of fiducial markers being a prerequisite, our aim was to assess its feasibility and safety and also to evaluate its success, from both the endoscopist's and radiotherapist's perspectives. Patients and methods ?We prospectively collected data concerning PDAC patients submitted to EUS-guided fiducial placement, from February 2018 to November 2019.?Technical success was defined as at least one marker presumed inside the tumor. Quality success was assessed at pre-SBRT computed tomography, accordingly to the number of markers inside or? less then ?1?cm from the tumor, number of markers at the tumor extremity, their location in different planes, the distance between them, and their distance from the biliary stent (if present). https://www.selleckchem.com/products/jnj-64619178.html A new quality score was then proposed and high-quality success defined as at least six of 12 points.